Estimation of Global Ocean TOA Instantaneous Clear‐Sky Albedo From CERES for Shortwave Cloud Radiative Effect Analysis Based on a Deep Learning Model
Bibliographic record
Abstract
Abstract Clouds play a crucial role in Earth's climate system, with clear‐sky albedo being fundamental for estimating cloud albedo and the shortwave (SW) cloud radiative effect (CRE), which are key to understanding Earth's radiative balance. However, direct satellite measurements of theoretical clear‐sky albedo for cloudy pixels are impossible. To address this limitation, we developed a Multi‐Layer Perceptron (MLP) model trained on over 20 million samples from the Clouds and the Earth's Radiant Energy System (CERES) data set, enabling the estimation of instantaneous clear‐sky albedo at the top of the atmosphere (TOA). The MLP model achieves an RMSE of 0.004 and R 2 of 0.96, having a closer agreement with direct observational products compared to other radiation products, and provides the temporally perfect match to the moderate resolution imaging spectroradiometer instantaneous observations. Furthermore, we correct undetected sub‐resolution cloud contamination and sea‐ice contamination within clear‐sky pixels present in CERES observations. Based on clear‐sky albedo across cloudy regions, the estimated instantaneous noon SW CRE is −113.44 W·m −2 . By employing another MLP model to scale the instantaneous clear‐sky albedo to daily values, the estimated daily CRE is −44.51 W·m −2 , which is 1.02 W·m −2 weaker than that from the CERES Synoptic TOA and surface fluxes and clouds (SYN) product, mainly since imperfect temporal match, as well as the differences in aerosol sources and treatment. The deep learning‐derived clear‐sky albedo and the estimated CRE provide a new approach for research on aerosol‐cloud interactions, cloud feedback mechanisms, and model improvements, offering valuable insights into the field.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".